US2021158959A1PendingUtilityA1

Learning method and information providing system

Assignee: INFORMATION SYSTEM ENG INCPriority: Mar 29, 2019Filed: Mar 25, 2020Published: May 27, 2021
Est. expiryMar 29, 2039(~12.7 yrs left)· nominal 20-yr term from priority
Inventors:Satoshi Kuroda
G06N 5/01G06N 3/0464G06N 3/09G06N 20/00G06V 10/761G06F 16/55G06F 16/5866G06F 16/583G06N 20/20G06N 20/10G16H 40/67G16H 40/20G16H 70/00G16H 30/40
49
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

The information providing system according to the present invention selects reference information that is appropriate when a user to perform a task related to a medical device works on the task, and has a first database that is built on machine learning, using a data structure for machine learning, and the data structure for machine learning includes a plurality of items of training data that each include evaluation target information, including image data, and a meta-ID, the image data includes an image that shows the medical device and an identification label for identifying the medical device, and the meta-ID is linked with a content ID that corresponds to the reference information.

Claims

exact text as granted — not AI-modified
1 . A learning method comprising:
 implementing machine learning using a data structure to build a first database, which a user to perform a task related to a medical device uses when selecting reference information that is appropriate when the user works on the task, wherein the data structure is stored in a storage unit provided in a computer,   wherein the data structure for machine learning comprises a plurality of items of training data that each include evaluation target information, including image data, and a meta-ID,   wherein the image data includes an image that shows the medical device and an identification label for identifying the medical device, and   wherein the meta-ID is linked with a content ID that corresponds to the reference information.   
     
     
         2 . An information providing system for selecting reference information that is appropriate when a user to perform a task related to a medical device works on the task, the information providing system comprising:
 a first database that is built on machine learning, using a data structure for machine learning,   wherein the data structure for machine learning comprises a plurality of items of training data that each include evaluation target information, including image data, and a meta-ID,   wherein the image data includes an image that shows the medical device and an identification label for identifying the medical device,   wherein the meta-ID is linked with a content ID that corresponds to the reference information, and   wherein the information providing system further comprises a hardware processor that is configured to select the reference information using the first database.   
     
     
         3 . An information providing system for selecting reference information that is appropriate when a user to perform a task related to a medical device works on the task, the information providing system comprising:
 a hardware processor that is configured to acquire acquired data including first image data, in which a specific medical device and a specific identification label for identifying the specific medical device are photographed; and   a first database that is built on machine learning, using a data structure for machine learning, which comprises a plurality of items of training data that each include evaluation target information including image data, and a meta-ID linked with the evaluation target information, wherein the image data included in the evaluation target information includes an image showing (i) the medical device and (ii) an identification label for identifying the medical device;   wherein the hardware processor is further configured to look up the first database and select a first meta-ID, among a plurality of meta-IDs, based on the acquired data;   wherein information providing system further comprises a second database that stores a plurality of content IDs linked with the meta-IDs, and a plurality of items of reference information corresponding to the content IDs; and   wherein the hardware processor is further configured to:   look up the second database and select a first content ID, among the plurality of content IDs, based on the first meta-ID; and   look up the second database and select first reference information, among the plurality of items of reference information, based on the first content ID.   
     
     
         4 . The information providing system according to  claim 3 , wherein the hardware processor is configured to generate a meta-ID list with the plurality of meta-IDs, generate a reference summary list that corresponds to the meta-ID list, and select the first meta-ID selected from the reference summary list. 
     
     
         5 . The information providing system according to  claim 3 ,
 wherein the hardware processor is further configured to acquire first video information;   wherein the information providing system further comprises a scene model database that stores past first video information, which is acquired in advance, scene information, which includes a scene ID linked with the past first video information, and three or more degrees of scene association between the past first video information and the scene information; and   wherein the hardware processor is further configured to:   look up the scene model database and acquire a scene ID list, which includes a first degree of scene association between the first video information and the scene information; and   generate a scene name list corresponding to the scene ID list; and   acquire the acquired data, which includes, as one pair, the first image data, and a first scene ID corresponding to a scene name selected from the scene name list.

Join the waitlist — get patent alerts

Track US2021158959A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.